Non-Contact Oxygen Saturation Measurement Using YCgCr Color Space with an RGB Camera

Abstract

Oxygen saturation (SPO₂) is an important indicator of health, and is usually measured by placing a pulse oximeter in contact with a finger or earlobe. However, this method has a problem in that the skin and the sensor must be in contact, and an additional light source is required. To solve these problems, we propose a non-contact oxygen saturation measurement technique that uses a single RGB camera in an ambient light environment. Utilizing the fact that oxygenated and deoxygenated hemoglobin have opposite absorption coefficients at green and red wavelengths, the color space of photoplethysmographic (PPG) signals recorded from the faces of study participants were converted to the YCgCr color space. Substituting the peaks and valleys extracted from the converted Cg and Cr PPG signals into the Beer-Lambert law yields the SPO₂ via a linear equation. When the non-contact SPO₂ measurement value was evaluated based on the reference SPO₂ measured with a pulse oximeter, the mean absolute error was 0.537, the root mean square error was 0.692, the Pearson correlation coefficient was 0.86, the cosine similarity was 0.99, and the intraclass correlation coefficient was 0.922. These results confirm the feasibility of non-contact SPO₂ measurements.

Keywords: Beer-Lambert law; YCgCr color space; hemoglobin; oxygen saturation; photoplethysmographic signal.

Figure 1

Wavelength-dependent absorption coefficients of oxygenated (solid line) and deoxygenated hemoglobin (dashed line).

Figure 2

Non-contact oxygen saturation measurement process. R = red; B = blue; G = green; ROI = region of interest; R_cgcr = Cr ratio/Cg ratio.

Figure 3

PPG signal acquisition process. The red line is the R raw signal, the green line is the G raw signal, and the blue line is B raw signal.

Figure 4

Process of extracting R_cgcr value from rPPG signal (a) R, G, B signals extracted from face ROI. The red line is the R raw signal, the green line is the G raw signal, and the blue line is B raw signal. (b) R, G, B signals are converted into YCgCr color space. The yellow line is the Y signal, the pink line is the Cr signal, and the light blue line is the Cg signal. (c) Result of bandpass filtering on Cg and Cr signals. The pink line is the filtered Cr signal, the light blue line is the filtered Cg signal. (d) The result of Equations (8) and (9). That is, the log value of the peak/valley extracted from the Cg and Cr signals to which bandpass filtering is applied, respectively. The pink line is the calculated Cr signal, the light blue line is the calculated Cg signal. (e) The result of Equation (10), that is, Cr ratio/Cg ratio.

Figure 5

Scatter plot showing the relationship between R_cgcr and the reference SPO₂.

Figure 6

Comparison of rSPO₂ obtained by non-contact and reference SPO₂ obtained by contact sensor. The black line is the reference SPO₂, the red line is the $${\mathrm{rSPO}}_2^{\mathrm{cgcr}}$$, and the blue line is the $${\mathrm{rSPO}}_2^{\mathrm{cbcr}}$$.